qi0dZddlmZddlmZej eZGddeZGddeZ Gdd eZ d gZ y ) zKOSMOS-2 model configuration)PreTrainedConfig)loggingcdeZdZdZdZdZdgZddddZ d fd ZxZ S) Kosmos2TextConfiga This is the configuration class to store the configuration of a [`Kosmos2TextModel`]. It is used to instantiate a KOSMOS-2 text decoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the text decoder of the KOSMOS-2 [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 65037): Vocabulary size of the Kosmos2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Kosmos2Model`]. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). embed_dim (`int`, *optional*, defaults to 2048): Dimensionality of the layers and the pooler layer. layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. ffn_dim (`int`, *optional*, defaults to 8192): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. scale_embedding (`bool`, *optional*, defaults to `True`): Scale embeddings by diving by sqrt(embed_dim). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). pad_token_id (`int`, *optional*, defaults to 1): Token id used for padding. bos_token_id (`int`, *optional*, defaults to 0): Token id used for beginning of string. eos_token_id (`int`, *optional*, defaults to 2): Token id used for end of string. ```kosmos_2_text_model text_configpast_key_valuesattention_heads embed_dimlayers)num_attention_heads hidden_sizenum_hidden_layersc .t|di|||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ | |_| |_| |_| |_| |_||_||_yN)super__init__ pad_token_id bos_token_id eos_token_idadd_cross_attention vocab_sizemax_position_embeddingsr r ffn_dimr activation_functiondropoutattention_dropoutactivation_dropout layerdroplayer_norm_epsinit_stdscale_embedding use_cache)selfrrr r rr rrrrr r!r"r#r$rrrrkwargs __class__s c/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/kosmos2/configuration_kosmos2.pyrzKosmos2TextConfig.__init__Us. "6"(((#6 $'>$"  .#6  !2"4",  .")i r*i gelu皙?r.r/h㈵>{Gz?TTF) __name__ __module__ __qualname____doc__ model_typebase_config_keykeys_to_ignore_at_inference attribute_mapr __classcell__r's@r(rrss2 h'J#O#4"50"%M $"!)+#+#r)rcDeZdZdZdZdZ dfd ZxZS)Kosmos2VisionConfiga This is the configuration class to store the configuration of a [`Kosmos2VisionModel`]. It is used to instantiate a KOSMOS-2 vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the KOSMOS-2 [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): The number of input channels. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). ```kosmos_2_vision_model vision_configc  t|di| ||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ yr)rrrintermediate_sizerr num_channels patch_size image_sizeinitializer_rangeinitializer_factorrr! hidden_act)r%rrDrr rErGrFrJr!rrHrIr&r's r(rzKosmos2VisionConfig.__init__sr "6"&!2!2#6 ($$!2"4!2,$r)) iir+r quick_gelur0r/r1g?)r5r6r7r8r9r:rr=r>s@r(r@r@sE$ L)J%O%%r)r@c:eZdZdZdZeedZ dfd ZxZ S) Kosmos2Configa This is the configuration class to store the configuration of a [`Kosmos2Model`]. It is used to instantiate a KOSMOS-2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the KOSMOS-2 [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) architecture. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Kosmos2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Kosmos2VisionConfig`]. latent_query_num (`int`, *optional*, defaults to 64): The number of latent query tokens that represent the image features used in the text decoder component. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether the model's input and output word embeddings should be tied. Example: ```python >>> from transformers import Kosmos2Config, Kosmos2Model >>> # Initializing a Kosmos-2 kosmos-2-patch14-224 style configuration >>> configuration = Kosmos2Config() >>> # Initializing a model (with random weights) from the kosmos-2-patch14-224 style configuration >>> model = Kosmos2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```zkosmos-2)rrBc P| t}tjdnt|tr tdi|}| t }tjdnt|tr t di|}||_||_||_||_ t|,di|y)NzR`text_config` is `None`. initializing the `Kosmos2TextConfig` with default values.zV`vision_config` is `None`. initializing the `Kosmos2VisionConfig` with default values.r) rloggerinfo isinstancedictr@rrBlatent_query_numtie_word_embeddingsrr)r%rrBrVrWr&r's r(rzKosmos2Config.__init__s  +-K KKl m  T *+:k:K  /1M KKp q  t ,/@-@M&* 0#6  "6"r))NN@T) r5r6r7r8r9rr@ sub_configsrr=r>s@r(rPrPs2 >J"3FYZK ##r)rPN) r8configuration_utilsrutilsr get_loggerr5rRrr@rP__all__rr)r(r^s\#3   H %i#(i#XG%*G%T;#$;#|  r)